Indian Journal of Science and Technology,
Год журнала:
2024,
Номер
17(23), С. 2421 - 2429
Опубликована: Май 28, 2024
Objective:
This
study
focuses
on
evaluating
the
accuracy
of
models
that
can
be
identified
by
taking
data
COVID-19-positive
cases
in
India.
Methods:
To
build
using
procedures,
Artificial
Neural
Networks
(ANN)
and
Auto
Regressive
Integrated
Moving
Average
(ARIMA).
The
has
been
taken
for
various
time
periods
(Covid-19
positive
cases)
from
March
2022
to
July
2023;
Nov.
2023.
was
collected
official
website
World
Health
Organization
(WHO).
traditional
ARIMA
Long
Short-Term
Memory
(LSTM)
deep
learning
methods
were
applied
periods.
Findings:
Model
performance
is
being
measured
with
error
parameter
(Root
Mean
Square
Error)
RMSE
(215.74,
100.36
127.81)
respectively
all
LSTM
performing
better
than
a
minimum
value
RMSE.
Novelty:
done
Covid-19
help
LSTM,
Bi-LSTM
methods.
outcome
these
gave;
accurate
best
model.
Keywords:
ARIMA,
Networks,
In
the
ongoing
COVID-19
pandemic,
digital
technologies
have
played
a
vital
role
to
minimize
spread
of
COVID-19,
and
control
its
pitfalls
for
general
public.
Without
such
technologies,
bringing
pandemic
under
would
been
tricky
slow.
Consequently,
exploration
status,
devising
appropriate
mitigation
strategies
also
be
difficult.
this
paper,
we
present
comprehensive
analysis
community-beneficial
that
were
employed
fight
pandemic.
Specifically,
demonstrate
practical
applications
ten
major
effectively
served
mankind
in
different
ways
during
crisis.
We
chosen
these
based
on
their
technical
significance
large-scale
adoption
arena.
The
selected
are
Internet
Things
(IoT),
artificial
intelligence(AI),
natural
language
processing(NLP),
computer
vision
(CV),
blockchain
(BC),
federated
learning
(FL),
robotics,
tiny
machine
(TinyML),
edge
computing
(EC),
synthetic
data
(SD).
For
each
technology,
working
mechanism,
context
challenges
from
perspective
COVID-19.
Our
can
pave
way
understanding
roles
COVID-19-fighting
used
future
infectious
diseases
prevent
global
crises.
Moreover,
discuss
heterogeneous
significantly
contributed
addressing
multiple
aspects
when
fed
aforementioned
technologies.
To
best
authors’
knowledge,
is
pioneering
work
transformative
with
broader
coverage
studies
applications.
Research Square (Research Square),
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 16, 2025
Abstract
Background
Given
the
unprecedented
surge
in
COVID-19
infections,
heightened
demand
for
medical
oxygen
prompted
numerous
national
and
global
initiatives
to
bridge
gap
between
supply
demand.
This
was
crucial
ensuring
adequate
treatment
patients
suffering
from
acute
respiratory
distress
syndrome
requiring
therapy.
research
aims
explore
factors
influencing
management
India
during
pandemic
beyond,
examining
both
facilitators
barriers.
Method
Through
a
thorough
review
of
literature,
secondary
research,
interviews
with
key
stakeholders,
critical
affecting
were
identified.
These
then
analyzed
using
modified
total
interpretive
structural
modeling
(m-TISM)
approach
MICMAC
(Matrice
d’
Impacts
croises
multiplication
applique
an
classment)
analysis
comprehend
their
hierarchical
relationships
driving
forces.
Results
The
study
identifies
fourteen
that
act
as
barriers
Covid-19
pandemic.
also
influence
non-pandemic
period.
development
m-TISM
model
gives
us
interrelationships
these
factors,
including
one
itself.
findings
identify
strategic
levers
strengthen
ecosystem
cross-sectoral
collaborations.
Conclusion
provides
insights
into
strengthening
ecosystem,
enabling
policymakers
program
implementers
make
informed
decisions
implement
pre-emptive
measures
address
future
threats
virus
or
similar
crises.
Indian Journal of Science and Technology,
Год журнала:
2024,
Номер
17(12), С. 1159 - 1166
Опубликована: Март 20, 2024
Objective:
The
importance
of
this
research
article
is
to
evaluate
efficient
model
for
diagnosing
pandemic
COVID-19
positive
cases
in
Telangana
State,
India.
Method:
Neural
Network
models
(Extreme
Learning
Machine
and
Multi-Layer
Perception),
Deep
(Long
Short
Term
Memory-LSTM)
traditional
Auto
Regressive
Integrated
Moving
Average
(ARIMA)
were
applied
the
data
was
converted
from
non-linear
linear
(stationarity)
forecasting
Covid-19
cases.
study
covered
1st.
Dec
2020
30th
May
2021.
80%
train
taken
fit
then
20%
test
used
predict
values.
deviation
between
original
predicted
led
an
error.
Among
these
error
values,
which
had
minimum
errors
considered
as
best
four
models.
Findings:
LSTM
proved
be
most
model,
a
result
least
Root
mean
square
(RMSE
=
71.12)
compared
ARIMA
(258.20),
ELM
(553.67)
MLP
(641.86)
Novelty:
These
methods
succour
forthcoming
days.
This
has
been
suggested
taking
better
preventive
steps
control
Keywords:
COVID19,
ARIMA,
LSTM,
MLP,
Forecasting
